Ant Colony Optimization Algorithm for Robot Path Planning with AFX-10

Ant Colony Optimization (ACO) is a method employed in computational science to find the “shortest path” in a dynamic environment. In nature, if an ant colony incurs an obstacle on their route to finding food, it has been studied that they will find the shortest path in getting to the nutrients. ACO can be applied to develop algorithms to determine the optimal route for an object to move in the case of encountering an obstacle. Utilizing computer simulation results from SWARM intelligence robotics studies, this paper will detail the implementation of an ACO algorithm on a physical robot. The robot, 5”x8”, was programmed with the algorithm and controlled autonomously via Jetson Nano, a microprocessor. The robot was placed in an area with an increasing number of obstacles to test its ability to avoid collision. The robot was tested in these environments with no obstacles, then increased by one obstacle until the robot could successfully find the shortest path in each area given two obstacles. The physical test runs in this dynamic environment were compared to simulation results to determine if the applied algorithm accurately and effectively found the shortest path for the robot